Nondestructive Detection of Ceramic Products Based on Tapping Sound Signal Feature Recogition

Abstract

Recent studies on the test of ceramic non-destructive testing are mainly based on high cost technologies, image processing and so on, these method possesses some drawback of low efficiency, high cost and so on. What’s more, detecting whether the ceramic products by human through listening to sound of tapping is also effectless. This paper proposed a non-destructive method for ceramic products to solve this problem. This non-destructive method consists of a tapping device and a signal processing module. The tapping device will be applied to generate the tapping sound signal and the signal processing system will be applied to analysis signal. After the process of signal analysis, sample length and peak of spectrum 2 parameters is extracted, then use these parameters to train SVM, the results will be compared with BP neural network (BPNN). The result of experiment shows that SVM with different kernels of linear, poly, rbf, sigmoid respectively reach the accuracy of 96.29%, 96.29%, 46.29%, 93.82%, while BPNN reaches the accuracy of 93.21%. This result proves that SVM can effectively complete the task of identifying defective ceramics, and its performance is better than BPNN.

Real-time hollow defect detection in tiles using on-device tiny machine learning

“…Our investigation substantially enhances existing methods in tile defect detection, as evidenced by a comprehensive comparison with prior studies [5][6][7][8][9][10][11][12][13][14] delineated in table 3. Our approach introduces a holistic improvement in several key performance indicators, warranting a detailed discussion on each advancement.…”